%matplotlib inline
import pandas as pd
import numpy as np
import math
import scipy

import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px
import plotly.graph_objects as go

import plotly.io as pio
pio.renderers.default = "plotly_mimetype+notebook"

Matplotlib

A simple plot

$y=sin(x)$

x = np.linspace(0, 2*math.pi, 100)
y = scipy.sin(x)
plt.plot(x,y)
# plt.savefig('line_plot.png', dpi=200)
plt.show()

Title

x = np.linspace(0, 2*math.pi, 10)
y = scipy.sin(x)
fig, ax = plt.subplots()
ax.plot(x,y)
ax.set_title('y = sin(x)')
plt.show()

Axes

x = np.linspace(0, 2*math.pi, 10)
y = scipy.sin(x)
fig, ax = plt.subplots()
ax.plot(x,y)
# set title
ax.set_title('y = sin(x)')
# horizontal axis
ax.set_xlabel('x')
# vertical axis
ax.set_ylabel('y')
plt.show()

/Users/localadmin/opt/anaconda3/envs/TIL6022/lib/python3.7/site-packages/ipykernel_launcher.py:2: DeprecationWarning:

scipy.sin is deprecated and will be removed in SciPy 2.0.0, use numpy.sin instead

Tick

Example from a matplotlib website

x = [1, 2, 3, 4]
y = [1, 4, 9, 6]
labels = ['Frogs', 'Hogs', 'Bogs', 'Slogs']

plt.plot(x, y)
# You can specify a rotation for the tick labels in degrees or with keywords.
plt.xticks(x, labels, rotation='vertical')
# Pad margins so that markers don't get clipped by the axes
plt.margins(0.2)
# Tweak spacing to prevent clipping of tick-labels
plt.subplots_adjust(bottom=0.15)
plt.show()

Line properties

For a complete list of line properties, visit this link

An example of line styles are shown bellow:

Source

x = np.linspace(0, 2*math.pi, 10)
y = scipy.sin(x)
fig, ax = plt.subplots()
ax.plot(
    x,y, 
    linestyle='dashdot', linewidth=3, 
    marker='o', markerfacecolor='r'
)
# set title
ax.set_title('y = sin(x)')
# horizontal axis
ax.set_xlabel('x')
# vertical axis
ax.set_ylabel('y')
plt.savefig('line_properties_example.png', dpi=200)
plt.show()

x = np.random.randn(1000)
plt.boxplot(x)
plt.show()

Histogram

x = np.random.randn(1000)
plt.hist(x, bins=100, rwidth=0.8)
plt.savefig('histogram_plot.png', dpi=200)
plt.show()

Hexbin

points = np.random.randn(1000,2)
plt.hexbin(x=points[:,0], y=points[:,1], gridsize=10, cmap='Spectral_r')
plt.savefig('hexbin_plot.png', dpi=200)
plt.show()

Grids

fig = plt.figure(figsize=(12, 9))
gs = fig.add_gridspec(nrows=2, ncols=2)
#
ax = fig.add_subplot(gs[:,0])
x = np.random.randn(1000)
ax.hist(x, bins=100, rwidth=0.8)
#
ax = fig.add_subplot(gs[0,1])
x = np.linspace(0, 2*math.pi, 100)
y = scipy.sin(x)
ax.plot(x,y)
#
ax = fig.add_subplot(gs[1,1])
x = np.linspace(0, 2*math.pi, 100)
y = scipy.cos(x)
ax.plot(x,y)

# plt.savefig('grids.png', dpi=200)
plt.show()

/Users/localadmin/opt/anaconda3/envs/TIL6022/lib/python3.7/site-packages/ipykernel_launcher.py:10: DeprecationWarning:

scipy.sin is deprecated and will be removed in SciPy 2.0.0, use numpy.sin instead

/Users/localadmin/opt/anaconda3/envs/TIL6022/lib/python3.7/site-packages/ipykernel_launcher.py:15: DeprecationWarning:

scipy.cos is deprecated and will be removed in SciPy 2.0.0, use numpy.cos instead

Challenge I

Add title and label to the figure above.

# YOUR CODE HERE

/Users/localadmin/opt/anaconda3/envs/TIL6022/lib/python3.7/site-packages/ipykernel_launcher.py:13: DeprecationWarning:

scipy.sin is deprecated and will be removed in SciPy 2.0.0, use numpy.sin instead

/Users/localadmin/opt/anaconda3/envs/TIL6022/lib/python3.7/site-packages/ipykernel_launcher.py:21: DeprecationWarning:

scipy.cos is deprecated and will be removed in SciPy 2.0.0, use numpy.cos instead

Seaborn

Scatterplot

iris dataset: multiple species with following information

• Sepal & petal
• Length and width

iris = sns.load_dataset('iris')
iris.head()

	sepal_length	sepal_width	petal_length	petal_width	species
0	5.1	3.5	1.4	0.2	setosa
1	4.9	3.0	1.4	0.2	setosa
2	4.7	3.2	1.3	0.2	setosa
3	4.6	3.1	1.5	0.2	setosa
4	5.0	3.6	1.4	0.2	setosa

sns.scatterplot(x='sepal_length', y='sepal_width', data=iris)
plt.show()

Challenge II

Color represents the hue

# YOUR CODE HERE

Relplot

sns.relplot(x='sepal_length', y='sepal_width', data=iris, hue='species')
plt.show()

sns.relplot(x='petal_length', y='petal_width', data=iris, hue='species')
# plt.savefig('iris_petal.png', dpi=300)
plt.show()

fmri = sns.load_dataset("fmri")
sns.relplot(data=fmri, x="timepoint", y="signal", kind="line")

<seaborn.axisgrid.FacetGrid at 0x7fbad2704f90>

Jointplot

tips dataset

tips = sns.load_dataset('tips')
tips.head()

	total_bill	tip	sex	smoker	day	time	size
0	16.99	1.01	Female	No	Sun	Dinner	2
1	10.34	1.66	Male	No	Sun	Dinner	3
2	21.01	3.50	Male	No	Sun	Dinner	3
3	23.68	3.31	Male	No	Sun	Dinner	2
4	24.59	3.61	Female	No	Sun	Dinner	4

sns.jointplot(x='total_bill', y='tip', data=tips)
# plt.savefig('total_bill_tip.png', dpi=200)
plt.show()

Boxplot / Violinplot

fig, ax = plt.subplots(ncols=2, figsize=(15,9))
sns.boxplot(x='species', y='petal_width', data=iris_data, ax=ax[0])
sns.violinplot(x='species', y='petal_width', data=iris_data, ax=ax[1])
# fig.savefig('iris_petal_width_dist.png', dpi=200)
plt.show()

FacetGrid

g = sns.FacetGrid(tips, col='sex', hue='smoker')
g.map(sns.scatterplot, 'total_bill', 'tip')
g.add_legend()
plt.savefig('smoker.png', dpi=200)
plt.show()

Heatmap

conf_mat = np.array([
    [85, 3, 2, 10, 0],
    [1, 80, 10, 1, 8],
    [0, 0, 70, 20, 10],
    [5, 2, 3, 75, 15],
    [10, 0, 0, 0, 90]
])
sns.heatmap(conf_mat, cmap='YlGn', annot=True)

# fix for mpl bug that cuts off top/bottom of seaborn viz
# https://github.com/mwaskom/seaborn/issues/1773
b, t = plt.ylim() # discover the values for bottom and top
b += 0.5 # Add 0.5 to the bottom
t -= 0.5 # Subtract 0.5 from the top
plt.ylim(b, t) # update the ylim(bottom, top) values

# plt.savefig('heatmap.png', dpi=200)
plt.show()

Plotly Express

df = px.data.iris() 
fig = px.scatter(df, x="sepal_length", y="sepal_width")
fig.show()

Challenge III

Add species as the color and hover is also species

# YOUR CODE HERE

df = px.data.tips()
fig = px.histogram(
    df, x="total_bill", y="tip", color="sex", 
    hover_data=df.columns
)
fig.show()

#load data
df_2007 = df.query('year==2007')
fig = px.bar(df_2007, x="pop", y="continent", orientation='h')
fig.show()

Challenge IV

# YOUR CODE HERE

Plotly Graph Objects

data_year = df.query("year==2007")
fig = go.Figure(data=go.Scatter(
    x = data_year['gdpPercap'],
    y = data_year['lifeExp'],
    mode='markers'
))
fig.update_xaxes(title_text="gdpPercap")
fig.update_yaxes(title_text="lifeExp")
#fig.update_xaxes(type="log")
fig.show()

fig = px.scatter(df.query("year==2007"), x="gdpPercap", y="lifeExp")
fig.show()

fig = px.scatter(df.query("year==2007"), x="gdpPercap", y="lifeExp", log_x=True)
fig.show()

Challenge V

Try to recreate the below figure using plotly express for population of 2007 from df.

• color is the continent
• size of the bubble is population
• hover is country

Hint

• Scatter functionality
• Scatter example

# YOUR CODE HERE